Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    KMS key

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     doğrud
    0.43
    定律
    0.40
    ıyordu
    0.39
    ከሰ
    0.38
    Radiux
    0.38
     މ
    0.38
    വൃ
    0.38
     vliegtuig
    0.38
    oying
    0.38
    愺
    0.38
    POSITIVE LOGITS
     requiring
    0.39
     NUM
    0.39
     contenant
    0.38
    তীত
    0.37
     Xan
    0.36
     sheets
    0.35
     Forms
    0.35
     outwards
    0.35
     substantive
    0.34
     Chore
    0.34
    Act Density 0.005%

    No Known Activations